Interactive tool reveals how graph models forecast weather and oceans
GNN-VIEW: Visual Inspection and Explanation of Graph-based Earth-System Models
Machine LearningHuman-Computer Interaction
Summary
Earth-system models use machine learning to predict weather and ocean conditions, but understanding how these models work can be difficult. The authors created GNN-VIEW, a tool that shows the connections inside graph-based models before and after training. This helps developers see if the model is built correctly and understand why certain predictions, like weather during a hurricane, might be wrong. Their tool works in a web browser and gives clear visual explanations to improve model building and debugging.
What this means in practice
- •For earth system model developers: Debug and understand graph structures during model building to improve forecasting accuracy before training.
- •For meteorology operations teams: Diagnose why weather forecasts fail by examining which input features the trained model used for predictions.
Authors
Alessandro Lucatelli, Ferdinand Unterhuber, Katharina Krenzer, Mennatallah El-Assady, Benedikt Soja, Christina Humer, Joel Oskarsson
Abstract
Machine learning Earth-system models are becoming increasingly important, and so is their development. Graph-based models, one of the most prominent approaches, allow developers to constrain the learning process before training via graph connectivity. Yet, developing these models remains challenging: the graph is built algorithmically with little intuition about the final result beyond static plotting, which requires extra work and is often not detailed enough. Even after successful training, how the model arrives at forecasts remains obscure. We present GNN-VIEW, an interactive browser-based tool that supports the development of such systems. GNN-VIEW exposes the graph's information pathways, allowing model developers to debug the graph structure before training. After training, GNN-VIEW uses attribution-based explainability to reveal which input features are used by the trained model for a given forecast. This helps developers understand why a model fails. We showcase the usefulness of GNN-VIEW in the construction stage of a graph for an ocean forecasting model, and in explaining poorly predicted precipitation of a trained weather forecasting model during Hurricane Laura.